activity
20122022
most citedEfficient Architecture Search by Network Transformation

320 citations · 1.7k across the 36 of their papers we have counts for

collaborators
Showing cs.LGShow all

24 papers · 1 filter

cs.LG2022★ 1 cited

Generative Adversarial Exploration for Reinforcement Learning

Weijun Hong, Menghui Zhu, Minghuan Liu +4

Exploration is crucial for training the optimal reinforcement learning (RL) policy, where the key is to discriminate whether a state visiting is novel. Most previous work focuses o…

cs.LG2022★ 24 cited

DropNAS: Grouped Operation Dropout for Differentiable Architecture Search

Weijun Hong, Guilin Li, Weinan Zhang +4

Neural architecture search (NAS) has shown encouraging results in automating the architecture design. Recently, DARTS relaxes the search process with a differentiable formulation t…

cs.LG2021

Bag of Tricks for Node Classification with Graph Neural Networks

Yangkun Wang, Jiarui Jin, Weinan Zhang +3

Over the past few years, graph neural networks (GNN) and label propagation-based methods have made significant progress in addressing node classification tasks on graphs. However,…

cs.LG2021

Towards Generalized Implementation of Wasserstein Distance in GANs

Minkai Xu, Zhiming Zhou, Guansong Lu +3

Wasserstein GANs (WGANs), built upon the Kantorovich-Rubinstein (KR) duality of Wasserstein distance, is one of the most theoretically sound GAN models. However, in practice it doe…

cs.LG2020★ 6 cited

Model-based Policy Optimization with Unsupervised Model Adaptation

Jian Shen, Han Zhao, Weinan Zhang +1

Model-based reinforcement learning methods learn a dynamics model with real data sampled from the environment and leverage it to generate simulated data to derive an agent. However…

cs.LG2020★ 53 cited

GeneraLight: Improving Environment Generalization of Traffic Signal Control via Meta Reinforcement Learning

Chang Liu, Huichu Zhang, Weinan Zhang +2

The heavy traffic congestion problem has always been a concern for modern cities. To alleviate traffic congestion, researchers use reinforcement learning (RL) to develop better tra…